Explorer is a LISP Machine from Texas Instruments. Its software starts with a vast body of software developed at MIT. Texas Instruments has stabilized that software and added more packages and utilities. This paper describes certain innovations in Texas Instrument's software for the Explorer. TI's software innovations were in two areas: increasing the learnability of this sophisticated system and adding software components as an aid to prototypers and software developers. Learning aid innovations are embodied in Suggestions Menus and the Universal Command Loop. Software component innovations are embodied in the Universal Command Loop, the Graphics Window System and Graphics Editor, the Relational Table Manager, and the Menu-Based Natural Language Interface. The innovations represented are of two kinds: innovations in concept(Suggestions Menus, Universal Command Loop, and Menu-Based Natural Language Interface) and innovations in design (Graphics Window System, Relational Table Manager).

This paper describes the NLMenu System, a menu-based natural language understanding system. Rather than requiring the user to type his input to the system, input to NLMenu is made by selecting items from a set of dynamically changing menus. Active menus and items are determined by a predictive left-corner parser that accesses a semantic grammar and lexicon. The advantage of this approach is that all inputs to the NLMenu System can be understood thus giving a 0% failure rate. A companion system that can automatically generate interfaces to relational databases is also discussed.

Conventional natural language interfaces suffer from several ease-of-use problems. They require a user to type and to formulate questions in a way that the system can understand. They have high failure rates which often frustrate users, and users often do not use features of the systems because they are unaware of them or don't trust them. In addition, conventional natural language systems are expensive to build and require large amounts of storage to use. This paper describes a new approach to natural language interfaces called menu-based natural language understanding. This new approach solves the problems listed above. The paper compares the menu-based natural language approach to conventional natural language interfaces and to other forms of interface and discusses the advantages and limitations of this new approach.

No abstract available.

It has been demonstrated that interactive natural language dialog is remarkably unruly, with many misspellings and grammatical errors. Although progress has been made in getting computers to process pristine English text, the day when computers will be able to process unlimited interactive natural language dialog is still very far off.The vast majority of the effort that has gone into designing interactive natural language systems has concentrated on the computer half of the human-computer dyad. Our approach concentrates on the human half. Specifically, the goal of our research is to define a human engineered subset of natural language that retains all of the user-oriented benefits of unrestricted natural language dialog, while greatly reducing the processing burden that true natural language interaction places on the computer. This paper is a preliminary examination of the possibility that these criteria may be satisfied by simply asking usres to be concise.